Guided filter

A guided filter is an edge-preserving smoothing image filter.

Uses your system voice; voice and rate in settings.

≈ 4 min read

Cite, export and learn8 citation formats · 8 exports · lesson and quiz

Names in other languages

No names in other languages are held for this entry yet.

Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.

(Learn how and when to remove this message)

A guided filter is an edge-preserving smoothing image filter. As with a bilateral filter, it can filter out noise or texture while retaining sharp edges.[1][2]

Comparison

edit edit source

Compared to the bilateral filter, the guided image filter has two advantages: bilateral filters have high computational complexity, while the guided image filter uses simpler calculations with linear computational complexity. Bilateral filters sometimes include unwanted gradient reversal artifacts and cause image distortion. The guided image filter is based on linear combination, making the output image consistent with the gradient direction of the guidance image, preventing gradient reversal.

Definition

edit edit source

One key assumption of the guided filter is that the relation between guidance I and the filtering output q is linear. Suppose that q is a linear transformation of I in a window ωk centered at the pixel k.

In order to determine the linear coefficient (ak,bk), constraints from the filtering input p are required. The output q is modeled as the input p with unwanted components n, such as noise/textures subtracted.

The basic model:

(1)  qi=akIi+bk,∀i∈ωk

(2)  qi=pi−ni

in which:

qi is the ith output pixel;
pi is the ith input pixel;
ni is the ith pixel of noise components;
Ii is the ith guidance image pixel;
(ak,bk) are some linear coefficients assumed to be constant in ωk.

The reason to use a linear combination is that the boundary of an object is related to its gradient. The local linear model ensures that q has an edge only if I has an edge, since ∇q=a∇I.

Subtract (1) and (2) to get formula (3);At the same time, define a cost function (4):

(3)  ni=pi−akIi−bk

(4)  E(ak,bk)=∑iϵωk((akIi+bk−pi)2+ϵak2)

in which

ϵ is a regularization parameter penalizing large ak;
ωk is a window centered at the pixel k.

And the cost function's solution is:

(5)  ak=1|ω|∑iϵωkIipi−μkpk¯σk2+ϵ

(6)  bk=pk¯−akμk

in which

μk and σk2 are the mean and variance of I in ωk;
|ω| is the number of pixels in ωk;
p¯k=1|ω|∑iϵωkpi is the mean of p in ωk.

After obtaining the linear coefficients (ak,bk), the filtering output qi is provided by the following algorithm:

Algorithm

edit edit source

By definition, the algorithm can be written as:

Algorithm 1. Guided Filter

edit edit source

input: filtering input image p ,guidance image I ,window radius r ,regularization ϵ

output: filtering output q

1.

meanI = fmean(I) meanp = fmean(p) corrI = fmean(I.∗I) corrIp = fmean(I.∗p)

2.

varI = corrI−meanI.∗meanI covIp = corrIp−meanI.∗meanp

3.

a = covIp./(varI+ϵ) b = meanp−a.∗meanI

4.

meana = fmean(a) meanb = fmean(b)

5.

q = meana.∗I+meanb

fmean is a mean filter with a wide variety of O(N) time methods.

Properties

edit edit source

Edge-preserving filtering

edit edit source

When the guidance image I is the same as the filtering input p. The guided filter removes noise in the input image while preserving clear edges.

Specifically, a “flat patch” or a “high variance patch” can be specified by the parameter ϵ of the guided filter. Patches with variance much lower than the parameter ϵ will be smoothed, and those with variances much higher than ϵ will be preserved. The role of the range variance σr2 in the bilateral filter is similar to ϵ in the guided filter. Both of them define the edge/high variance patches that should be kept and noise/flat patches that should be smoothed.”

Gradient-preserving filtering

edit edit source

When using the bilateral filter to filter an image, artifacts may appear on the edges. This is because of the pixel value's abrupt change on the edge. These artifacts are inherent and hard to avoid, because edges appear in all kinds of pictures.

The guided filter performs better in avoiding gradient reversal. Moreover, in some cases, it can be ensured that gradient reversal does not occur.

Structure-transferring filtering

edit edit source

Due to the local linear model of q=aI+b, it is possible to transfer the structure from the guidance I to the output q. This property enables some special filtering-based applications, such as feathering, matting and dehazing.

Implementations

edit edit source

See also

edit edit source

References

edit edit source
  1. ^ He, Kaiming; Sun, Jian; Tang, Xiaoou (2013). "Guided Image Filtering". IEEE Transactions on Pattern Analysis and Machine Intelligence. 35 (6): 1397–1409. doi:10.1109/TPAMI.2012.213. PMID 23599054. Wikipedia revision 1258164511, retrieved 2026-11-18
  2. ^ Guided Image Filtering Wikipedia revision 1258164511, retrieved 2026-11-18
  3. ^ "Guided filtering of images - MATLAB imguidedfilter". Wikipedia revision 1258164511, retrieved 2026-11-18
  4. ^ "OpenCV: Filters". Wikipedia revision 1258164511, retrieved 2026-11-18
  5. ^ "FFmpeg Filters Documentation". Wikipedia revision 1258164511, retrieved 2026-11-18

Text derived from https://en.wikipedia.org/w/index.php?oldid=1258164511 under CC BY-SA 4.0; modifications have been made.

Words in each sectionDefinitionDefinitionDefinition: 382 words382PropertiesPropertiesProperties: 227 words227ComparisonComparisonComparison: 70 words70ImplementationsImplementationsImplementations: 15 words15See alsoSee alsoSee also: 5 words5
Words in each section. Measured from the stored article body; sections below the minimum are not plotted.

Provenance

snapshot enwiki-001258164511 · captured 2024-11-18 · ledger · version history

Cite this page as: encyclopegia.org, “Guided filter”, snapshot enwiki-001258164511. https://encyclopegia.org/a/guided-filter